© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98558
    Prev
    Next
    INDEX
    Explanations

    articles followed by technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens—especially multi-digit numbers, decimals, and percentages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     what
    -1.54
    corrhi
    -1.46
    zdo
    -1.44
     which
    -1.41
     this
    -1.39
    さんへ
    -1.36
     wiedzieć
    -1.30
    Ꮀ
    -1.27
     altavoz
    -1.27
     atasan
    -1.26
    POSITIVE LOGITS
    </em>
    1.19
     没有
    1.16
     公司
    1.15
     to
    1.13
    sp
    1.13
     纯
    1.10
    捞
    1.05
    特的
    1.05
     use
    1.05
     户型
    1.05
    Activations Density 0.007%

    No Known Activations